Research map / Vision-language and multimodal / Human and embodied modeling
Multi-Task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Joint collaborative MCN instead of the strongest listed baseline | REC · RefCOCO testB | Acc@0.5: 69.99 -> 74.98 | Helped |
| Joint collaborative MCN instead of the strongest listed baseline | RES · RefCOCO+ testB | IoU: 41.56 -> 44.69 | Helped |
| Use MCN instead of MattNet | REC · RefCOCOg val | Acc@0.5: 66.67 -> 66.46 | Hurt |
| Use MCN instead of MattNet | REC · RefCOCOg test | Acc@0.5: 67.27 -> 66.01 | Hurt |
| Add TextAtt (ablation) | MCN (Base) · RefCOCO val | REC Acc@0.5: 77.45 -> 77.65 | Helped |
| Add GARAN (ablation) | MCN with TextAtt · RefCOCO val | REC Acc@0.5: 77.65 -> 79.20 | Helped |
| Add CEM (ablation) | MCN with GARAN · RefCOCO val | RES IoU: 59.07 -> 61.61 | Helped |
| Add CEM (ablation) | MCN with GARAN · RefCOCO val | IE: 13.37% -> 10.37% | Helped |
| Add ASNLS (ablation) | MCN with CEM · RefCOCO val | RES IoU: 61.61 -> 62.44 | Helped |
| Add ASNLS (ablation) | MCN with CEM · RefCOCO val | IE: 10.37% -> 6.65% | Helped |
| Use Soft-NLS post-processing (ablation) | MCN RES output · RefCOCO val | IoU: 61.61 -> 62.27 | Helped |
| Use RoI Crop hard post-processing (ablation) | MCN RES output · RefCOCO val | IoU: 61.61 -> 61.19 | Hurt |
Closest papers by meaning
- Rethinking Two-Stage Referring Expression Comprehension: A Novel Grounding and Segmentation Method Modulated by Point (AAAI 2024 · similarity 0.91)
- DViN: Dynamic Visual Routing Network for Weakly Supervised Referring Expression Comprehension (CVPR 2025 · similarity 0.89)
- WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and Segmentation (CVPR 2025 · similarity 0.89)
- Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension (AAAI 2025 · similarity 0.88)
- A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era (NeurIPS 2024 · similarity 0.88)
- Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks (ICLR 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.